0

我正在尝试使用并行后端在超参数网格上caret训练模型。xgboost

下面是一些代码，它使用Give Me Some Creditcaret数据来演示为的超参数网格搜索设置并行后端。

library(plyr)
library(dplyr)
library(pROC)
library(caret)
library(xgboost)
library(readr)
library(parallel)
library(doParallel)

if(exists("xgboost_cluster")) stopCluster(xgboost_cluster)
hosts = paste0("192.168.18.", 52:53)
xgboost_cluster = makePSOCKcluster(hosts, master="192.168.18.51")

# load the packages across the cluster
clusterEvalQ(xgboost_cluster, {
  deps = c("plyr", "Rcpp", "dplyr", "caret", "xgboost", "pROC", "foreach", "doParallel")
  for(d in deps) library(d, character.only = TRUE)
  rm(d, deps)
})

registerDoParallel(xgboost_cluster)  
# load in the training data
df_train = read_csv("04-GiveMeSomeCredit/Data/cs-training.csv") %>%
  na.omit() %>%                                                                # listwise deletion 
  select(-`[EMPTY]`) %>%
  mutate(SeriousDlqin2yrs = factor(SeriousDlqin2yrs,                           # factor variable for classification
                                   labels = c("Failure", "Success")))
# set up the cross-validated hyper-parameter search
xgb_grid_1 = expand.grid(
  nrounds = 1000,
  eta = c(0.01, 0.001, 0.0001),
  max_depth = c(2, 4, 6, 8, 10),
  gamma = 1
)

# pack the training control parameters
xgb_trcontrol_1 = trainControl(
  method = "cv",
  number = 5,
  verboseIter = TRUE,
  returnData = FALSE,
  returnResamp = "all",                                                        # save losses across all models
  classProbs = TRUE,                                                           # set to TRUE for AUC to be computed
  summaryFunction = twoClassSummary,
  allowParallel = TRUE
)

# train the model for each parameter combination in the grid, 
#   using CV to evaluate
xgb_train_1 = train(
  x = as.matrix(df_train %>%
                  select(-SeriousDlqin2yrs)),
  y = as.factor(df_train$SeriousDlqin2yrs),
  trControl = xgb_trcontrol_1,
  tuneGrid = xgb_grid_1,
  method = "xgbTree"
)

我检查了所有核心hosts都被用于训练，但在master节点上，没有使用任何进程。这是预期的行为吗？有什么方法可以改变这种行为并利用主节点上的核心进行处理？

4

1 回答 1

1

为了利用主节点进行处理，您只需添加'localhost'到hosts，如下所示：

hosts = c("localhost", paste0("192.168.18.", 52:53))

这会将您的主节点上的一个核心添加到集群中，然后将其用于处理。如果要添加多个内核，只需传入更多'localhost'.

hosts = c(rep('localhost', detectCores()), paste0("192.168.18.", 52:53))
于 2015-11-16T16:50:15.210 回答